# 1. Rename Columns
renamed_movies <- movies %>%
rename(
movie_title = Film , # Rename 'movie_title' to 'Film'
release_year = Year # Rename 'release_year' to 'Year'
)
head(renamed_movies)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Por… Roma… The Weinstei… 70 1.75
## 2 Youth in Revolt Come… The Weinstei… 52 1.09
## 3 You Will Meet a Tall Dar… Come… Independent 35 1.21
## 4 When in Rome Come… Disney 44 0
## 5 What Happens in Vegas Come… Fox 72 6.27
## 6 Water For Elephants Drama 20th Century… 72 3.08
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>#2 Select Columns
movies_selected <- renamed_movies %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`)
# Print the first 6 rows of the selected dataset
head(movies_selected)## # A tibble: 6 × 5
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 Zack and Miri Make a Por… 2008 Roma… 1.75 64
## 2 Youth in Revolt 2010 Come… 1.09 68
## 3 You Will Meet a Tall Dar… 2010 Come… 1.21 43
## 4 When in Rome 2010 Come… 0 15
## 5 What Happens in Vegas 2008 Come… 6.27 28
## 6 Water For Elephants 2011 Drama 3.08 60#3 Filter Columns
movies_filtered <- renamed_movies %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80)
# View the first 6 rows of the filtered dataset
head(movies_filtered)## # A tibble: 6 × 8
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animati… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animati… Disney 88 1.37
## 4 Rachel Getting Married Drama Independent 61 1.38
## 5 My Week with Marilyn Drama The Weinstei… 84 0.826
## 6 Midnight in Paris Romence Sony 84 8.74
## # ℹ 3 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>#4 Mutate to Add New Column
movies_filtered <- movies_filtered %>%
mutate(Profitability_millions = Profitability / 1e6)
# Print the first 6 rows of the dataset with the new column
head(movies_filtered)## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animati… Disney 89 2.90
## 2 Waitress Romance Independent 67 11.1
## 3 Tangled Animati… Disney 88 1.37
## 4 Rachel Getting Married Drama Independent 61 1.38
## 5 My Week with Marilyn Drama The Weinstei… 84 0.826
## 6 Midnight in Paris Romence Sony 84 8.74
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>#5 Arrange Dataset
movies_sorted <- movies_filtered %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
# Print the first 6 rows of the sorted dataset
head(movies_sorted)## # A tibble: 6 × 9
## movie_title Genre `Lead Studio` `Audience score %` Profitability
## <chr> <chr> <chr> <dbl> <dbl>
## 1 WALL-E Animation Disney 89 2.90
## 2 Midnight in Paris Romence Sony 84 8.74
## 3 Enchanted Comedy Disney 80 4.01
## 4 Knocked Up Comedy Universal 83 6.64
## 5 Waitress Romance Independent 67 11.1
## 6 A Serious Man Drama Universal 64 4.38
## # ℹ 4 more variables: `Rotten Tomatoes %` <dbl>, `Worldwide Gross` <chr>,
## # release_year <dbl>, Profitability_millions <dbl>#6 Combine Functions
final_df <- movies %>%
rename(
movie_title = Film,
release_year = Year
) %>%
select(movie_title, release_year, Genre, Profitability, `Rotten Tomatoes %`) %>%
filter(release_year > 2000, `Rotten Tomatoes %` > 80) %>%
mutate(Profitability_millions = Profitability / 1e6) %>%
arrange(desc(`Rotten Tomatoes %`), desc(Profitability_millions))
# Print the first 6 rows of the final combined dataset
head(final_df)## # A tibble: 6 × 6
## movie_title release_year Genre Profitability `Rotten Tomatoes %`
## <chr> <dbl> <chr> <dbl> <dbl>
## 1 WALL-E 2008 Animation 2.90 96
## 2 Midnight in Paris 2011 Romence 8.74 93
## 3 Enchanted 2007 Comedy 4.01 93
## 4 Knocked Up 2007 Comedy 6.64 91
## 5 Waitress 2007 Romance 11.1 89
## 6 A Serious Man 2009 Drama 4.38 89
## # ℹ 1 more variable: Profitability_millions <dbl>print(names(movies))## [1] "Film" "Genre" "Lead Studio"
## [4] "Audience score %" "Profitability" "Rotten Tomatoes %"
## [7] "Worldwide Gross" "Year"#7 Interpret the Final Dataframe Interpretation: The data shows a trend that higher Rotten Tomatoes percentages often correlate with higher profitability; however, there are exceptions where some less profitable films receive high ratings. This indicates that while critical acclaim may contribute to popularity, it does not always guarantee box office success
#8 Extra Credit
summary_df <- movies %>%
rename(
movie_title = Film,
release_year = Year
) %>%
group_by(Genre) %>%
summarize(
average_rating = mean(`Rotten Tomatoes %`, na.rm = TRUE),
average_profitability_millions = mean(Profitability / 1e6, na.rm = TRUE)
)
# Print the summary dataframe
print(summary_df)## # A tibble: 10 × 3
## Genre average_rating average_profitability_millions
## <chr> <dbl> <dbl>
## 1 Action 11 0.00000125
## 2 Animation 74.2 0.00000376
## 3 Comdy 13 0.00000265
## 4 Comedy 42.7 0.00000378
## 5 Drama 51.5 0.00000841
## 6 Fantasy 73 0.00000178
## 7 Romance 42.1 0.00000398
## 8 Romence 93 0.00000874
## 9 comedy 87 0.00000810
## 10 romance 54 0.000000653